End of training

README.md

@@ -17,12 +17,12 @@ model-index:
       name: imdb
       type: imdb
       config: plain_text
-      split: test
+      split: train
       args: plain_text
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.93164
+      value: 0.9664
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2350
-- Accuracy: 0.9316
+- Loss: 0.1123
+- Accuracy: 0.9664
 
 ## Model description
 
@@ -64,8 +64,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.2207        | 1.0   | 1563 | 0.2531          | 0.9125   |
-| 0.1537        | 2.0   | 3126 | 0.2350          | 0.9316   |
+| 0.2348        | 1.0   | 1407 | 0.1712          | 0.9432   |
+| 0.1443        | 2.0   | 2814 | 0.1123          | 0.9664   |
 
 
 ### Framework versions